Lab_Extra1_CatieKitrinosMarkup

library(tidyverse)

## ── Attaching packages ──────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

## ── Conflicts ─────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

Data for the lab

time_series_confirmed_long <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")) %>%
  rename(Province_State = "Province/State", Country_Region = "Country/Region")  %>% 
               pivot_longer(-c(Province_State, Country_Region, Lat, Long),
                             names_to = "Date", values_to = "Confirmed") 

## Parsed with column specification:
## cols(
##   .default = col_double(),
##   `Province/State` = col_character(),
##   `Country/Region` = col_character()
## )

## See spec(...) for full column specifications.

# Let's get the times series data for deaths
time_series_deaths_long <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv")) %>%
  rename(Province_State = "Province/State", Country_Region = "Country/Region")  %>% 
  pivot_longer(-c(Province_State, Country_Region, Lat, Long),
               names_to = "Date", values_to = "Deaths")

## Parsed with column specification:
## cols(
##   .default = col_double(),
##   `Province/State` = col_character(),
##   `Country/Region` = col_character()
## )
## See spec(...) for full column specifications.

# Create Keys 
time_series_confirmed_long <- time_series_confirmed_long %>% 
  unite(Key, Province_State, Country_Region, Date, sep = ".", remove = FALSE)
time_series_deaths_long <- time_series_deaths_long %>% 
  unite(Key, Province_State, Country_Region, Date, sep = ".") %>% 
  select(Key, Deaths)
# Join tables
time_series_long_joined <- full_join(time_series_confirmed_long,
    time_series_deaths_long, by = c("Key")) %>% 
    select(-Key)
# Reformat the data
time_series_long_joined$Date <- mdy(time_series_long_joined$Date)
# Create Report table with counts
time_series_long_joined_counts <- time_series_long_joined %>% 
  pivot_longer(-c(Province_State, Country_Region, Lat, Long, Date),
               names_to = "Report_Type", values_to = "Counts")

Fine tuning ggplots

# Plot graph to a pdf outputfile
pdf("time_series_example_plot.pdf", width=6, height=3)
time_series_long_joined %>% 
  group_by(Country_Region,Date) %>% 
  summarise_at(c("Confirmed", "Deaths"), sum) %>% 
  filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
    geom_point() +
    geom_line() +
    ggtitle("US COVID-19 Deaths")
dev.off()

## png 
##   2

Plot to PNG

ppi <- 300
png("time_series_example_plot.png", width=6*ppi, height=6*ppi, res=ppi)
time_series_long_joined %>% 
  group_by(Country_Region,Date) %>% 
  summarise_at(c("Confirmed", "Deaths"), sum) %>% 
  filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
    geom_point() +
    geom_line() +
    ggtitle("US COVID-19 Deaths")
dev.off()

## png 
##   2

R Markdown Loading Images

US COVID-19 Deaths

Interactive graphs

# Version 2
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(ggplot2)
ggplotly(
  time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
      geom_point() +
      geom_line() +
      ggtitle("US COVID-19 Deaths")
 )

library(plotly)
# Subset the time series data to include US deaths
US_deaths <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region == "US")
# Collect the layers for agraph of the US time series data for covid deaths
 p <- ggplot(data = US_deaths, aes(x = Date,  y = Deaths)) + 
        geom_point() +
        geom_line() +
        ggtitle("US COVID-19 Deaths")
# Plot the graph using ggplotly
ggplotly(p)

Animated Graphs with gganimate

Creating the animations

library(gganimate)
library(transformr)
theme_set(theme_bw())

library(gifski)
data_time <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("China","Korea, South","Japan","Italy","US")) 
p <- ggplot(data_time, aes(x = Date,  y = Confirmed, color = Country_Region)) + 
      geom_point() +
      geom_line() +
      ggtitle("Confirmed COVID-19 Cases") +
      geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
# Some people needed to use this line instead
animate(p,renderer = gifski_renderer(), end_pause = 15)
animate(p, end_pause = 15)

library(gapminder)
library(gganimate)
library(gifski)

data_time <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("China","Korea, South","Japan","Italy","US")) 
p <- ggplot(data_time, aes(x = Date,  y = Confirmed, color = Country_Region)) + 
      geom_point() +
      geom_line() +
      ggtitle("Confirmed COVID-19 Cases") +
      geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
# Some people needed to use this line instead
animate(p,renderer = gifski_renderer(), end_pause = 15)

anim_save("deaths_5_countries.gif", p)

Exercises

Challenge 1

###Print a graph (different from the one above) to a png file using 3*ppi for the height and width and display the png file in the report using the above R Markdown format.

ppi <- 300
png("countries_I_lived_in_counts.png", width=3*ppi, height=3*ppi, res=ppi)
time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("US", "Japan","Spain","Ecuador")) %>% 
    ggplot(aes(x = Date,  y = Deaths, color = Country_Region)) + 
    geom_point() +
    geom_line() +
    ggtitle("COVID-19 Deaths")
    dev.off()

## png 
##   2

COVID-19 Deaths In Countries I Used to Live In

Challenge 2

###Turn one of the exercises from Lab 5 into an interactive graph with plotyly

library(gifski)
time_data <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("US", "Brazil","United Kingdom","Italy","Mexico", "France","Spain","India","Iran","Peru"))
    p <- ggplot(time_data, aes(x = Date,  y = Deaths, color = Country_Region)) + 
    geom_point() +
    geom_line() +
    ggtitle("COVID-19 Deaths Top 10 Countries") +
    geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
    
animate(p,renderer = gifski_renderer(), end_pause = 15)

Challenge 3

###Create an animated graph of your choosing using the time series data to display an aspect (e.g. states or countries) of the data that is important to you.

lived_deaths <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("US", "Japan","Spain","Ecuador"))
 p <- ggplot(lived_deaths, aes(x = Date,  y = Deaths, color = Country_Region)) + 
    geom_point() +
    geom_line() +
    ggtitle("COVID-19 Deaths In Countries I Lived In") +
    geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
    
animate(p,renderer = gifski_renderer(), end_pause = 15)